COORDINATED STABILIZING CONTROL FOR THE EXCITER AND GOVERNOR LOOPS USING FUZZY SET-THEORY AND NEURAL NETS

This paper presents a design technique for a new hydropower plant cont roller using fuzzy set theory and artificial neural networks. The cont roller is suitable for real time operation, with the aim of improving the generating unit transients by acting through the exciter input, th e guide vane and the runner blade positions. The developed fuzzy logic based controller (FLC) whose control signals are adjusted using the o n-line measurements, can offer better damping effects for generator os cillations over a wider range of operating conditions than conventiona l regulators. Digital simulations of a hydropower plant equipped with a low-head Kaplan turbine are performed and the comparisons of convent ional excitation-governor control, optimal state-feedback control and FLC performances are presented. The FLC, based on a set of fuzzy logic operations that are performed on controller inputs, provides a means of converting linguistic control requirements based on expert knowledg e into an efficient control strategy. A fuzzy associative matrix is ge nerated by using unsupervised learning of artificial neural networks. Results obtained on the nonlinear hydrounit mathematical model simulat ion demonstrate that the performance of the FLC closely agrees with th at obtained if the optimal state-feedback multivariable discrete-rime controller is applied. (C) 1997 Elsevier Science Ltd.